Target tracking in a collaborative sensor network

In a collaborative sensor network (CSN), the conventional target tracking algorithms employed are Kalman filtering (KF) or extended Kalman filtering (EKF). However, these techniques have a presumed probability distribution of the system noise and prediction noise. They also need some a priori information that may be unavailable in some circumstances. Therefore, the system is not flexible for a complicated scenario. With the help of a machine learning technique called expert prediction (EP), a novel target tracking approach for CSNs is developed. This scheme makes use of the aforementioned EP in parameter estimation course for the target of interest, instead of exploiting the filtering method as typically found in available literature. This idea is further unfolded with comparisons regarding the CSN using Kalman filters, extended Kalman filters, and decentralized sigma-point information filters (DSPIFs). The new tracking algorithm is investigated with both linear and nonlinear prediction methods. Simulation results demonstrate that this proposed measure will deliver forecasting output with more precision because of the built-in multimodel mode among different experts, the learning ability, and the self-perfection characteristic. Not only does this performance occur in a more robust way than those of the existing approaches – particularly in the presence of heavy clutter, highly maneuvering targets, and/or multiple targets – but it simultaneously requires the least a priori information and imposes the least limitation on the observation model.